/*
 * void crosscall1(void (*fn)(void), void (*setg_gcc)(void *g), void *g)
 *
 * Calling into the gc tool chain, where all registers are caller save.
 * Called from standard MIPS N64 ABI, where $16-$23, $28, $30, and $f24-$f31
 * are callee-save, so they must be saved explicitly, along with $31 (LR).
 */
.globl crosscall1
.set noat
crosscall1:
#ifndef __mips_soft_float
	daddiu	$29, $29, -160
#else

// the user should prepare stack space in advance.
// SAVE_R22_TO_R31(offset) saves R22 ~ R31 to the stack space
// of ((offset)+0*8)(R3) ~ ((offset)+9*8)(R3).
//
// SAVE_F24_TO_F31(offset) saves F24 ~ F31 to the stack space
// of ((offset)+0*8)(R3) ~ ((offset)+7*8)(R3).
//
// Note: g is R22

#define SAVE_R22_TO_R31(offset)	\
	MOVV	g,   ((offset)+(0*8))(R3)	\
	MOVV	R23, ((offset)+(1*8))(R3)	\

/*
 * void crosscall1(void (*fn)(void), void (*setg_gcc)(void *g), void *g)
 *
 * Calling into the gc tool chain, where all registers are caller save.
 * Called from standard lp64d ABI, where $r1, $r3, $r23-$r30, and $f24-$f31
 * are callee-save, so they must be saved explicitly, along with $r1 (LR).
 */
.globl crosscall1
crosscall1:
	addi.d	$r3, $r3, -160
	st.d	$r1, $r3, 0
	st.d	$r23, $r3, 8
	st.d	$r24, $r3, 16

	sd	x25, 80(sp)
	sd	x26, 88(sp)
	sd	x27, 96(sp)
	fsd	f8, 104(sp)
	fsd	f9, 112(sp)
	fsd	f18, 120(sp)
	fsd	f19, 128(sp)
	fsd	f20, 136(sp)
	fsd	f21, 144(sp)
	fsd	f22, 152(sp)
	fsd	f23, 160(sp)
	fsd	f24, 168(sp)
	fsd	f25, 176(sp)
	fsd	f26, 184(sp)
	fsd	f27, 192(sp)

	// a0 = *fn, a1 = *setg_gcc, a2 = *g
	mv	s1, a0
	mv	s0, a1
	mv	a0, a2
	jalr	ra, s0	// call setg_gcc (clobbers x30 aka g)

	MOVV	R19, (8*7)(R29)
	MOVV	R20, (8*8)(R29)
	MOVV	R21, (8*9)(R29)
	MOVV	R22, (8*10)(R29)
	MOVV	R23, (8*11)(R29)
	MOVV	RSB, (8*12)(R29)
	MOVV	g, (8*13)(R29)
	MOVV	R31, (8*14)(R29)
#ifndef GOMIPS64_softfloat
	MOVD	F24, (8*15)(R29)
	MOVD	F25, (8*16)(R29)
	MOVD	F26, (8*17)(R29)
	MOVD	F27, (8*18)(R29)
	MOVD	F28, (8*19)(R29)
	MOVD	F29, (8*20)(R29)
	MOVD	F30, (8*21)(R29)
	MOVD	F31, (8*22)(R29)
#endif

	f13 = f12 * 13
	f14 = f13 * 14
	f15 = f14 * 15
	f16 = f15 * 16
	f17 = f16 * 17
	f18 = f17 * 18
	f19 = f18 * 19
	f20 = f19 * 20
	f21 = f20 * 21
	f22 = f21 * 22
	f23 = f22 * 23
	f24 = f23 * 24
	f25 = f24 * 25
	f26 = f25 * 26
	f27 = f26 * 27
	f28 = f27 * 28
	f29 = f28 * 29
	f30 = f29 * 30
	f31 = f30 * 31
	f32 = f31 * 32
	f33 = f32 * 33
	f34 = f33 * 34
	f35 = f34 * 35
	f36 = f35 * 36

	MOVW	R21, (4*9)(R29)
	MOVW	R22, (4*10)(R29)
	MOVW	R23, (4*11)(R29)
	MOVW	g, (4*12)(R29)
	MOVW	R31, (4*13)(R29)
#ifndef GOMIPS_softfloat
	MOVD	F20, (4*14)(R29)
	MOVD	F22, (4*14+8*1)(R29)
	MOVD	F24, (4*14+8*2)(R29)
	MOVD	F26, (4*14+8*3)(R29)
	MOVD	F28, (4*14+8*4)(R29)
	MOVD	F30, (4*14+8*5)(R29)
#endif
	JAL	runtime·load_g(SB)

	JAL	runtime·cgocallback(SB)

	MOVW	(4*4)(R29), R16
	MOVW	(4*5)(R29), R17

	sw	$18, 12($29)
	sw	$19, 16($29)
	sw	$20, 20($29)
	sw	$21, 24($29)
	sw	$22, 28($29)
	sw	$23, 32($29)
	sw	$30, 36($29)

#ifndef __mips_soft_float
	sdc1	$f20, 40($29)
	sdc1	$f22, 48($29)
	sdc1	$f24, 56($29)
	sdc1	$f26, 64($29)
	sdc1	$f28, 72($29)
	sdc1	$f30, 80($29)
#endif
	move	$20, $4 // save R4
	move	$4, $6
	jalr	$5	// call setg_gcc
	jalr	$20	// call fn

	lw	$16, 4($29)
	lw	$17, 8($29)

	FSTPD (F18, F19), 376(RSP)
	FSTPD (F20, F21), 392(RSP)
	FSTPD (F22, F23), 408(RSP)
	FSTPD (F24, F25), 424(RSP)
	FSTPD (F26, F27), 440(RSP)
	FSTPD (F28, F29), 456(RSP)
	FSTPD (F30, F31), 472(RSP)
	CALL ·asyncPreempt2(SB)
	FLDPD 472(RSP), (F30, F31)
	FLDPD 456(RSP), (F28, F29)
	FLDPD 440(RSP), (F26, F27)
	FLDPD 424(RSP), (F24, F25)
	FLDPD 408(RSP), (F22, F23)
	FLDPD 392(RSP), (F20, F21)
	FLDPD 376(RSP), (F18, F19)

				{1, 9223372034707292160}, // F0 F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13 F14 F15 F16 F17 F18 F19 F20 F21 F22 F23 F24 F25 F26 F27 F28 F29 F30 F31
			},
			outputs: []outputInfo{
				{0, 9223372034707292160}, // F0 F1 F2 F3 F4 F5 F6 F7 F8 F9 F10 F11 F12 F13 F14 F15 F16 F17 F18 F19 F20 F21 F22 F23 F24 F25 F26 F27 F28 F29 F30 F31
			},
		},
	},